agentleFS
Sign inStart free
epamepam/ketcher/.agents/skills/generate-autotests/SKILL.md

generate-autotests

Skill927 starsChanged 2 days agoApache-2.0View on GitHub

Generate a Playwright autotest for Ketcher from an Autotest Request issue. Use when asked to write an autotest from an Autotest Request, or when the claude-implement-autotests workflow dispatches it.

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read .memory-bank/testing/testing.md and the Autotest Request details.

    line 14
  2. Distinctive:

    Before writing spec code in an interactive run, get approval as testing.md requires ("E2E Test Plans").

    line 15
  3. Very specific:

    Write the spec under ketcher-autotests/tests/specs/, following testing.md for file location and for any page object or helper you add.

    line 17
  4. Distinctive:

    Run the new spec with the commands in testing.md ("How to Run E2E Tests") and record the result.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are a QA automation engineer for Ketcher, an open-source chemical structure editor (TypeScript/React). Generate a Playwright autotest based on Autotest Request issue number (AUTOTEST_REQUEST_NUMBER), title (AUTOTEST_REQUEST_TITLE), url (AUTOTEST_REQUEST_URL) and details (AUTOTEST_REQUEST_DETAILS).

Conventions

.memory-bank/testing/testing.md is the only source for E2E conventions: imports, fixtures, page objects, selectors, naming, the comment block, and what to avoid. Read it before writing anything and follow it. This file covers only what is specific to generating tests from an Autotest Request.

Steps

  1. Read .memory-bank/testing/testing.md and the Autotest Request details. Find the existing page objects and helpers that cover the scenario (testing.md, "Page Objects and Helpers").
  2. Before writing spec code in an interactive run, get approval as testing.md requires ("E2E Test Plans").
    • Known exception: the claude-implement-autotests.yml workflow runs this skill with no user to answer, so it writes the spec without asking. This stays until a later change edits the workflow.
  3. Write the spec under ketcher-autotests/tests/specs/, following testing.md for file location and for any page object or helper you add.
  4. Run the new spec with the commands in testing.md ("How to Run E2E Tests") and record the result.

Comment block

The Test task line of the comment block is AUTOTEST_REQUEST_URL. The rest of the block follows testing.md.

Output

  • The spec file path, and the path of every page object or helper you created.
  • The result of the spec run.
  • Any testing.md convention you could not follow, with the reason.
  • Git commits follow the git rules in AGENTS.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free